BaseTask

BaseTask(
   api, background = False, **kwargs
)

---

Deep Deterministic Policy Gradient

Arguments

actor_model (keras.nn.Model instance): See Model for details. critic_model (keras.nn.Model instance): See Model for details. optimizer (keras.optimizers.Optimizer instance): See Optimizer for details. action_inp (keras.layers.Input / keras.layers.InputLayer instance): See Input for details. tau (float): tau. gamma (float): gamma.

Methods:

.background

.background()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.help

.help()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.run

.run()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.running

.running()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.start

.start()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

.stop

.stop()

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

TaskState

TaskState()

---

Deep Deterministic Policy Gradient

Arguments

actor_model (keras.nn.Model instance): See Model for details. critic_model (keras.nn.Model instance): See Model for details. optimizer (keras.optimizers.Optimizer instance): See Optimizer for details. action_inp (keras.layers.Input / keras.layers.InputLayer instance): See Input for details. tau (float): tau. gamma (float): gamma.

---

TaskInfo

TaskInfo()

---

Deep Deterministic Policy Gradient

Arguments

actor_model (keras.nn.Model instance): See Model for details. critic_model (keras.nn.Model instance): See Model for details. optimizer (keras.optimizers.Optimizer instance): See Optimizer for details. action_inp (keras.layers.Input / keras.layers.InputLayer instance): See Input for details. tau (float): tau. gamma (float): gamma.

---

on_begin

.on_begin(
   name, *args, **kwargs
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

on_error

.on_error(
   name, *args, **kwargs
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

on_end

.on_end(
   name, *args, **kwargs
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

create

.create(
   api
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

get_class

.get_class(
   name
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.

---

get

.get(
   api, name, kwargs, background
)

---

Remember the transaction.

Accepts a state, action, reward, next_state, terminal transaction.

Arguments

transaction (abstract): state, action, reward, next_state, terminal transaction.